K-nearest Neighbor Classifier Research Articles

Investigation of early detection possibilities of sugar beet disease with machine learning algorithms based on multispectral reflection

Traditionally, diagnosis and monitoring of agricultural diseases are carried out through on-site observation and inspection. These methods are time-consuming and may represent limited samples. Therefore, remote sensing technology has become an important tool in disease detection and monitoring in agriculture. In the research, Cercospora leaf spot (Cercospora beticola sacc.) disease, which cause significant economic losses in sugar beet production, were detected in the early stages using machine learning algorithms using non-invasive multispectral images taken with UAV under field conditions is intended to be determined. The research was fulfilled using images from the grower fields in two regions where the disease was observed intensively. Index value data from digital surface model maps created by processing the images taken were used as training and test data. Numerical data was tested using five different supervised machine learning methods. The success of the analyzed models in predicting disease formation from the index values obtained from the images taken and the physiological changes that occur before the disease agents appear on sugar beet leaves was over 70%. Among the models compared in the study, the k-nearest neighbor classifier (KNN) model gave the highest success in both diseases, with 83% accuracy and 76% and 86% f1-score values. The support vector machines model followed the KNN model with 77% accuracy, 75%, and 86% f1-score values. According to the results of the research, it has been revealed that plant diseases have the potential for pre-symptomatic detection, and by processing the images obtained with UAV-based MS images, it is possible to detect diseases in the early period.

A machine learning approach to evaluate the impact of virtual balance/cognitive training on fall risk in older women.

Novel technologies based on virtual reality (VR) are creating attractive virtual environments with high ecological value, used both in basic/clinical neuroscience and modern medical practice. The study aimed to evaluate the effects of VR-based training in an elderly population. The study included 36 women over the age of 60, who were randomly divided into two groups subjected to balance-strength and balance-cognitive training. The research applied both conventional clinical tests, such as (a) the Timed Up and Go test, (b) the five-times sit-to-stand test, and (c) the posturographic exam with the Romberg test with eyes open and closed. Training in both groups was conducted for 10 sessions and embraced exercises on a bicycle ergometer and exercises using non-immersive VR created by the ActivLife platform. Machine learning methods with a k-nearest neighbors classifier, which are very effective and popular, were proposed to statistically evaluate the differences in training effects in the two groups. The study showed that training using VR brought beneficial improvement in clinical tests and changes in the pattern of posturographic trajectories were observed. An important finding of the research was a statistically significant reduction in the risk of falls in the study population. The use of virtual environments in exercise/training has great potential in promoting healthy aging and preventing balance loss and falls among seniors.

Comparing Texture Analysis of Apparent Diffusion Coefficient MRI in Hepatocellular Adenoma and Hepatocellular Carcinoma.

This study aimed to assess the effectiveness of using MRI-apparent diffusion coefficient (ADC) map-driven radiomics to differentiate between hepatocellular adenoma (HCA) and hepatocellular carcinoma (HCC) features. The study involved 55 patients with liver tumors (20 with HCA and 35 with HCC), featuring 106 lesions equally distributed between hepatic carcinoma and hepatic adenoma who underwent texture analysis on ADC map MR images. The analysis identified several imaging features that significantly differed between the HCA and HCC groups. Four classification models were compared for distinguishing HCA from HCC including linear support vector machine (linear-SVM), radial basis function SVM (RBF-SVM), random forest (RF), and k-nearest neighbor (KNN). The k-nearest neighbor (KNN) classifierdisplayed the top accuracy (0.89) and specificity (0.90). Linear-SVM and KNN classifiers showcased the leading sensitivity (0.88) for both, with the KNN classifier achieving the highest precision (0.9). In comparison, the conventional interpretation had lower sensitivity (70.1%) and specificity (77.9%). The study found that utilizing ADC maps for texture analysis in MR images is a viable method to differentiate HCA from HCC, yielding promising results in identified texture features.

Spiking neural network with local plasticity and sparse connectivity for audio classification

Purpose. Studying the possibility of implementing a data classification method based on a spiking neural network, which has a low number of connections and is trained based on local plasticity rules, such as Spike-Timing-Dependent Plasticity. Methods. As the basic architecture of a spiking neural network we use a network included an input layer and layers of excitatory and inhibitory spiking neurons (Leaky Integrate and Fire). Various options for organizing connections in the selected neural network are explored. We have proposed a method for organizing connectivity between layers of neurons, in which synaptic connections are formed with a certain probability, calculated on the basis of the spatial arrangement of neurons in the layers. In this case, a limited area of connectivity leads to a higher sparseness of connections in the overall network. We use frequency-based coding of data into spike trains, and logistic regression is used for decoding. Results. As a result, based on the proposed method of organizing connections, a set of spiking neural network architectures with different connectivity coefficients for different layers of the original network was implemented. A study of the resulting spiking network architectures was carried out using the Free Spoken Digits dataset, consisting of 3000 audio recordings corresponding to 10 classes of digits from 0 to 9. Conclusion. It is shown that the proposed method of organizing connections for the selected spiking neural network allows reducing the number of connections by up to 60% compared to a fully connected architecture. At the same time, the accuracy of solving the classification problem does not deteriorate and is 0.92...0.95 according to the F1 metric. This matches the accuracy of standard support vector machine, k-nearest neighbor, and random forest classifiers. The source code for this article is publicly available: https://github.com/sag111/Sparse-WTA-SNN.

Enhanced Recommender Systems with the Removal of Fake User Profiles

The rapid expansion of information resources on the internet has made it increasingly challenging for users to get valuable and relevant information. Recommendation systems (RSs) play a vital role in addressing this issue by providing personalized suggestions based on user preferences. However, the open nature of RSs allows for the injection of fake profiles by malicious users, leading to biased ratings and manipulation of the overall system results. These fake profiles have been intended to promote or degrade specific items, which creates bias in the system and compromises the user experience. The motivation behind these fake profiles is to promote or degrade a particular item, which affects the system and makes it more biased toward certain items. This research paper aims to detect and eliminate such fake profiles in RSs, ensuring users receive genuine and reliable results. The proposed approach utilizes a voting ensemble (VE) method, combining the strengths of multiple classification algorithms including Quadratic Discriminant Analysis (QDA), K-Nearest Neighbor (KNN), and Naive Bayes classifier (NBC). By utilizing these classifiers, the system enhances its robustness against malicious activities. The proposed VE method effectively identifies the fake profiles with a minimum number of parameters, and it shows high detection accuracy on Movielens datasets. It has been demonstrated that the proposed method gives 99.4%, 99.5%, 99.4% and 99.6% accuracy using NBC, QDA, KNN, and VE, respectively and it outperforms all other competing methods in terms of accuracy, precision, recall and MCC.

Can the attributes of an app predict its rating?

When Google Play Store developers first publish their apps, it may seem that their success comes from the roll of a dice. Ways to improve the rating of their app may seem impossible to glean, with many relying on blind guessing to determine ways forward. In this paper, we hypothesize that the attributes of a Google Play Store apps, including maturity level, install count, and price, can estimate its rating, or stars out of five. We believed that comparing three models trained on these attributes, each with unique architectures, would lead to a higher final accuracy than one. By using Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) classifiers, we found that the attributes of an app can predict its rating, with review count, date of last update, and storage size being the most influential attributes. During modeling, we found that the RF classifier most successfully predicted the rating of an app, getting 79.3% of predictions correct. These results suggest a connection between the rating of an app and its attributes. The results from this paper can inform app developers and investors about improvement paths to increase the rating of their app, thereby increasing its success.

Diabetes prediction using feature engineering and machine learning algorithms with security

The prevalence of diabetes has been steadily increasing, necessitating accurate prediction models to assist in early diagnosis and proactive management. In this paper, a hybrid machine learning-based diabetes prediction model has been proposed. To evaluate the model, the dataset was subsequently divided into training and testing subsets. We used the Random Forest Classifier, Light Gradient Boosting Mechanism Classifier, Gradient Boosting Classifier, Logistic Regression, K-Nearest Neighbours (KNN) Classifier, Naive Bayes Gaussian, Decision Tree Classifier, XGBoost Classifier, and Support Vector Classifier as nine different classifiers. Several metrics were used to evaluate the models, including testing accuracy, recall score, F1 score, and precision score. We have evaluated our model on the “Pima Indian Diabetes Database”[1], which served as the main dataset, for diabetes prediction. The proposed model serves as a practical framework for researchers and practitioners interested in leveraging machine learning techniques for diabetes prediction.

LOCAL FEATURE SELECTION USING THE WRAPPER APPROACH FOR FACIAL EXPRESSION RECOGNITION

Automatic Facial Expression Recognition (FER) systems provide an important way to express and interpret the emotional and mental states of human beings. These FER systems transform the facial image into a set of features to train a classifier capable of distinguishing between different classes of emotions. However, the problem often posed is that the extracted feature vectors sometimes contain irrelevant or redundant features, which decreases the accuracy of the induced classifier and increases the computation time. To overcome this problem, dimensionality must be reduced by selecting only the most relevant features. In this paper, we study the impact of adding the "Wrapper" selection approach and using the information provided by different local regions of the face such as the mouth, eyes and eyebrows, on the performance of a traditional FER system based on a local geometric feature extraction method. The objective here is to test and analyze how this combination can improve the overall performance of the original traditional system. The obtained results, based on the Multimedia Understanding Group (MUG) database, showed that the FER system combined with the proposed feature selection strategy gives better classification results than to the original system for all four classification models, namely, K-Nearest Neighbor (KNN) classifier, Tree classifier, NB classifier and Linear Discriminant Analysis (LDA). Indeed, a considerable reduction (up to 50%) in the number of features used and an accuracy of 100%, using the LDA classifier, were observed, which represents a significant improvement in terms of computation time, efficiency and memory space. Furthermore, the majority of relevant features used are part of the "eyebrows region", which proves the importance of using information from local regions of the face in emotion recognition tasks.

An Efficient Sarcasm Detection using Linguistic Features and Ensemble Machine Learning

Sarcasm detection in written text has emerged as a significant research area within natural language processing (NLP). Sarcasm, characterized by conveying the opposite of the intended meaning often for humor, irony, or ridicule, poses a challenge due to its contextual and tonal nuances. This study investigates the application of machine learning methods to detect sarcasm in text due to its potential to reverse the overall sentiment expressed in a sentence. A total of 13 linguistic manually crafted features related to text meaning, word usage, lexical diversity, and readability are extracted. These features are then employed to train a variety of machine learning models including Gradient Boosting, Decision Tree, Random Forest, Support Vector Machine, Gaussian Nave Bayes, K-Nearest Neighbor, and Logistic Regression classifiers. Additionally, an Ensemble Model and a Dense Neural Network is developed, both trained on the extracted handcrafted features to showcase performance. The results reveal that the suggested ensemble model achieves a peak accuracy of 93% in sarcasm detection. The amalgamation of these 13 linguistic features enhances model performance when compared to other contemporary models, exhibiting an improvement of up to 5% in terms of F1-score using the publicly available gold standard News Headline Dataset.

Decoding Human Somatosensory Sensitivity Through Resting EEG and Behavioral Analysis: A Multimodal Fusion Approach.

In precision medicine and clinical pain management, the creation of quantitative, objective indicators to assess somatosensory sensitivity was essential. This study proposed a fusion approach for decoding human somatosensory sensitivity, which combined multimodal (quantitative sensory test and neurophysiology) features to classify the dataset on individual somatosensory sensitivity and reveal distinct types of brain activation patterns. Sixty healthy participants took part in the experiment on somatosensory sensitivity that implemented cold, heat, mechanical punctate, and pressure stimuli, and the resting-state electroencephalography (EEG) was collected using BrainVision. The quantitative sensory testing (QST) scores of the participants were clustered using the unsupervised k-means algorithm into four subgroups: generally hypersensitive (HS), generally non-sensitive (NS), predominantly thermally sensitive (TS), and predominantly mechanically sensitive (MS). Furthermore, two types of power spectral density (PSD), band-based PSD (BB-PSD) and frequency-based PSD (FB-PSD), and two types of inter-electrode connectivity (IEC), band-based connectivity (BBC) and frequency-based connectivity (FBC), derived from resting-state EEG were subjected to feature selection with a proposed prior-compared minimum-redundancy maximum-relevance (PCMRMR) protocol. Their effectiveness was then tested by the supervised classification tasks using support vector machine (SVM), k-nearest neighbor (kNN), random forest (RF), and Gaussian classifier (GC). Brain networks of four somatosensory types were revealed by decoding fused multimodal data, namely type-averaged connectivity. The data from sixty healthy individuals were divided into training (n =59) and validation (n =1) datasets according to leave-one-subject-out (LOSO) criteria. The FBC was identified, which can serve as better brain signatures than BB-PSD, FB-PSD, and BBC to classify subjects as HS, NS, TS, or MS groups. Using the SVM, kNN, RF, and GC models, the best accuracy of 87% was obtained when classifying participants into HS, NS, TS, or MS groups. Moreover, the brain networks were decoded from HS, NS, TS, and MS groups by decoding the type-averaged connectivity fused from somatosensory phenotypes and selected FBC. It indicated that quantified multi-parameter somatosensory sensitivity could be achieved with acceptable accuracy, leading to considerable possibilities for using objective pain perception evaluation in clinical practice.

Ensemble Based Approach: Evaluating network and Model Performance Tackling DDOS attack

With in the dynamic realm of cyber threats, distributed denial of service (DDoS) attacks pose a serious threat. They can undermine network infrastructures and bring about service interruptions that cost money. Our research proposes an ensemble-based technique for DDoS attack detection in response to this problem. By combining the strengths of three distinct classifiers—Random Forest, K-Nearest Neighbors (KNN), and Adaboost—we create a powerful ensemble model. To ensure superior performance, we employ a Multi-Layer Perceptron (MLP) for intricate feature extraction and data normalization in the pre-processing stage. Together with individual classifiers, the ensemble's efficiency is carefully evaluated, verifying that it can accurately identify and counteract DDoS attacks. Motivated by the dynamic nature of DDoS attacks and their inability to be defended against by conventional defense mechanisms, our work is the first to apply machine learning to enhance detection. Ensemble approaches hold promise in addressing the evolving DDoS threat landscape because they combine multiple classifiers to enhance overall performance. The research adds a new dimension by combining MLP-based feature extraction with the Adaboost, KNN, and Random Forest classifiers to increase the discriminatory power of the model. Some of our objectives include building an ensemble-based DDoS attack detection system, evaluating individual classifier performance, comparing ensemble performance with individual classifiers, and using data normalization and MLP-based feature extraction. The research is methodically organized, with a literature review, methodology, performance analysis, ensemble approach analysis, and a concluding summary. The outcomes show the value of the recommended ensemble approach and pave the way for more advancements in DDoS attack detection methods, enhancing online service security and availability in the face of evolving cyber threats.

A Data Fusion Approach for Accurate Diagnosis of Parkinson's Disease

Diagnosing Parkinson's Disease (PD) can be quite challenging as it presents with symptoms and lacks biomarkers. Nevertheless, the use of data fusion, which combines types of data using machine learning techniques holds promise, for the timely detection of the disease. In this study, we explore the application of data fusion by employing Principal Component Analysis (PCA) as a step to reduce complexity. We then utilize the K Nearest Neighbors (KNN) classification to improve the accuracy of PD diagnosis. By analyzing nonlinear features associated with PD from a dataset PCA helps us extract attributes while maintaining important variations in the data. Subsequently, KNN is employed to identify patterns in this reduced feature space and effectively distinguish between individuals with PD and those who are healthy. Our results show improvements when using the KNN classifier compared to state-of-the-art approaches. This demonstrates its effectiveness in detecting PD leading to promising outcomes and providing a framework for precise PD diagnosis.

An influence-based k-nearest neighbour classifier for classification of data with different densities

An influence-based k-nearest neighbour classifier for classification of data with different densities

An Integrated Business Intelligence Framework for Sustainable Risk Mitigation

This research paper examines the critical juncture of business intelligence and sustainable risk management in response to the increasing challenges faced by modern businesses. Our study recognizes that organizations must navigate uncertainties while prioritizing sustainability. It focuses on analyzing credit risk data. We present a comprehensive examination of predictive performance using Logistic Regression, Decision Tree, and K-Nearest Neighbors classifiers augmented by the Synthetic Minority Over-sampling Technique (SMOTE) for class rebalancing. The empirical findings presented through detailed tables and figures reveal intricate relationships and patterns within the data. This research also contributes to the broader discourse on responsible business practices by highlighting the integration of business intelligence in sustainable risk mitigation. Moreover, comparative analysis of machine learning algorithms under various resampling techniques further strengthens the framework’s reliability.

An Efficient Ensemble Algorithm for Boosting k-Nearest Neighbors Classification Performance via Feature Bagging

An Efficient Ensemble Algorithm for Boosting k-Nearest Neighbors Classification Performance via Feature Bagging

K-Nearest Neighbor Classifier for Uncertain Data in Feature Space

K-Nearest Neighbor Classifier for Uncertain Data in Feature Space

Enhancing Alzheimer's Disease Diagnosis: Leveraging Convolutional Neural Networks for Feature Extraction and KNN Classification

Detecting Alzheimer's disease (AD) accurately is crucial for early patient management, allowing for proactive steps to minimize irreversible brain damage. AD-related cognitive decline varies in severity, from mild cognitive impairment to mild, moderate, and severe dementia. Early AD detection serves various purposes, such as reducing healthcare costs, slowing brain degeneration, and enhancing treatment outcomes. Machine learning techniques, especially in MRI image analysis, have gained significance in AD diagnosis. In our research, we've employed a deep learning model with convolutional layers for extracting essential information from MRI scans. Additionally, we've utilized the gray wolf meta-heuristic algorithm to identify optimal features. These features are then used in a K-nearest neighbors (KNN) classifier to categorize AD into three distinct types (very mild, mild, and moderate) while distinguishing normal and healthy cases. Our approach achieved an impressive accuracy rate of 95.6% when tested.

Comparison of Naive Bayes, K-Nearest Neighbor, and Support Vector Machine Classification Methods in Semi-Supervised Learning for Sentiment Analysis of Kereta Cepat Jakarta Bandung (KCJB)

Transportation technology has developed very rapidly in the 21st century; one of them is high-speed trains. Currently, the Indonesian government is implementing the construction of the Kereta Cepat Jakarta-Bandung (KCJB) project in collaboration with China. The construction of this fast train project has attracted various comments and opinions from the public on Twitter and social media. This research aims to compare the classification methods of Naïve Bayes, K-Nearest Neighbor (K-NN), and Support Vector Machine (SVM) in classifying sentiment in tweets about high-speed trains obtained by scraping Twitter. The comparison process was carried out using semi-supervised learning, and the results showed that the semi-supervised SVM model had the best performance with an average accuracy of 86%, followed by the semi-supervised Naïve Bayes model and semi-supervised K-NN with an average accuracy of 81% and 58% respectively. Overall, the prediction results from the three models conclude that there are more tweets with negative sentiment than tweets with positive and neutral sentiment.

Detection method of early heart valve diseases based on heart sound features

Heart valve disease (HVD) is one of the common cardiovascular diseases. Heart sound is an important physiological signal for diagnosing HVDs. This paper proposed a model based on combination of basic component features and envelope autocorrelation features to detect early HVDs. Initially, heart sound signals lasting 5 minutes were denoised by empirical mode decomposition (EMD) algorithm and segmented. Then the basic component features and envelope autocorrelation features of heart sound segments were extracted to construct heart sound feature set. Then the max-relevance and min-redundancy (MRMR) algorithm was utilized to select the optimal mixed feature subset. Finally, decision tree, support vector machine (SVM) and k-nearest neighbor (KNN) classifiers were trained to detect the early HVDs from the normal heart sounds and obtained the best accuracy of 99.9% in clinical database. Normal valve, abnormal semilunar valve and abnormal atrioventricular valve heart sounds were classified and the best accuracy was 99.8%. Moreover, normal valve, single-valve abnormal and multi-valve abnormal heart sounds were classified and the best accuracy was 98.2%. In public database, this method also obtained the good overall accuracy. The result demonstrated this proposed method had important value for the clinical diagnosis of early HVDs.

Classifying and clustering mood disorder patients using smartphone data from a feasibility study

Differentiating between bipolar disorder and major depressive disorder can be challenging for clinicians. The diagnostic process might benefit from new ways of monitoring the phenotypes of these disorders. Smartphone data might offer insight in this regard. Today, smartphones collect dense, multimodal data from which behavioral metrics can be derived. Distinct patterns in these metrics have the potential to differentiate the two conditions. To examine the feasibility of smartphone-based phenotyping, two study sites (Mayo Clinic, Johns Hopkins University) recruited patients with bipolar I disorder (BPI), bipolar II disorder (BPII), major depressive disorder (MDD), and undiagnosed controls for a 12-week observational study. On their smartphones, study participants used a digital phenotyping app (mindLAMP) for data collection. While in use, mindLAMP gathered real-time geolocation, accelerometer, and screen-state (on/off) data. mindLAMP was also used for EMA delivery. MindLAMP data was then used as input variables in binary classification, three-group k-nearest neighbors (KNN) classification, and k-means clustering. The best-performing binary classification model was able to classify patients as control or non-control with an AUC of 0.91 (random forest). The model that performed best at classifying patients as having MDD or bipolar I/II had an AUC of 0.62 (logistic regression). The k-means clustering model had a silhouette score of 0.46 and an ARI of 0.27. Results support the potential for digital phenotyping methods to cluster depression, bipolar disorder, and healthy controls. However, due to inconsistencies in accuracy, more data streams are required before these methods can be applied to clinical practice.